Abstract
Objective U-Net technology is implemented for image segmentation to diagnose cases of intestinal obstruction. To evaluate the application value of somatostatin combined with transanal intestinal obstruction decompression catheter in the treatment of distal colonic malignant intestinal obstruction and to explore the therapeutic effect of somatostatin on acute abdomen surgery in patients with intestinal obstruction. Methods After the segmentation technique, a retrospective analysis of 30 patients with acute and complete distal colonic malignant obstruction treated by surgery was divided into a control group and an observation group according to a random number table. The treatment efficiency, clinical symptoms, disappearance time after treatment, and the incidence of complications were compared between the two groups of patients. Results The image segmentation using U-Net can effectively assist in the medical diagnosis of the colon. Our study found that patients with combined treatment with somatostatin and anal intestinal obstruction catheter were relieved of preoperative abdominal pain and abdominal distension; compared with the abdominal circumference at the time of admission, the abdominal circumference was significantly reduced. Abdominal examination was performed 3 days after comprehensive treatment, and combined with computed tomography (CT), we observed that the measured maximum transverse diameter of the proximal colon was significantly smaller than that before treatment. Before treatment, all patients were divided into a control group and a treatment group. After treatment, the symptoms of the two groups of patients were alleviated. The treatment effective rate of the observation group was 93.3%, and the treatment effective rate of the control group was 73.3%. The effective rate was significantly higher than that of the control group, and the difference was statistically significant. Conclusions Through the use of image segmentation technology, somatostatin treatment of early inflammatory bowel obstruction after acute abdomen surgery can effectively improve the treatment efficiency of patients, shorten the disappearance of clinical symptoms, reduce the incidence of complications, and have a significant therapeutic effect, which is worthy of clinical application. Somatostatin combined with enteral obstruction catheter treatment is safe and effective for elderly patients with acute distal large bowel malignant intestinal obstruction. It has a higher completion rate of laparoscopic surgery and a first-stage anastomosis power, which reduces the risk of perioperative period and reduces the patient's financial burden.
Highlights
Many computer vision tasks require intelligent segmentation of images to understand the content of the image and make it easier to analyze each part
After continuous somatostatin pumping and decompression tube treatment through anorectal obstruction for 4 to 10 days, the average (5:6 ± 1:2) days were compared with the abdominal circumference at admission (100%), and the abdominal circumference before surgery was significantly reduced; it is 81 ± 2:3% (P ≤ 0:001)
After 4 to 7 days and an average of 4:2 ± 1:1 days of treatment, compared with the abdominal circumference at admission (100%), the abdominal circumference before surgery was reduced to 88 ± 1:3% (P = 0:01); abdominal computed tomography (CT) examination was performed 3 days after treatment to measure the maximum transverse diameter of the proximal colon was 4:6 ± 0:5 cm, which was less than 6:3 ± 0:6 cm before treatment (P = 0:02)
Summary
Many computer vision tasks require intelligent segmentation of images to understand the content of the image and make it easier to analyze each part. Today’s image segmentation technology uses deep learning models to accurately understand the real world, which was unimaginable ten years ago. Image segmentation uses a computer to distinguish the content of an image, which is a very challenging task in a computer vision system. Semantic segmentation is to classify all pixels in an image, and pixels with the same semantics are segmented. There has been an increasing demand for image segmentation in industries such as smart medical care, autonomous driving, indoor navigation, human-computer interaction, virtual or augmented reality, robotics, image. Computational and Mathematical Methods in Medicine beautification, and smart agriculture. The learned image segmentation algorithm serves as technical support
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Computational and mathematical methods in medicine
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
